lederhosen 1.1.0 → 1.1.1

data/lederhosen.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "lederhosen"
-  s.version = "1.1.0"
+  s.version = "1.1.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Austin G. Davis-Richardson"]
@@ -27,6 +27,7 @@ Gem::Specification.new do |s|
     "lib/lederhosen.rb",
     "lib/lederhosen/cli.rb",
     "lib/lederhosen/tasks/cluster.rb",
+    "lib/lederhosen/tasks/join_otu_tables.rb",
     "lib/lederhosen/tasks/make_udb.rb",
     "lib/lederhosen/tasks/otu_filter.rb",
     "lib/lederhosen/tasks/otu_table.rb",

data/lib/lederhosen/tasks/join_otu_tables.rb

@@ -0,0 +1,59 @@
+require 'set'
+
+module Lederhosen
+
+  class CLI
+
+    desc 'join_otu_tables', 'combine multiple otu tables'
+
+    method_option :input,  :type => :string, :required => true
+    method_option :output, :type => :string, :required => true
+
+    def join_otu_tables
+
+      input = Dir[options[:input]]
+      output = options[:output]
+
+      ohai "combining #{input.size} file(s) and saving to #{output}"
+
+      all_otu_names = Set.new
+      all_samples = Set.new
+
+      sample_name_count = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = 0 } }
+
+      # read all of the csv files
+      input.each do |input_file|
+        File.open(input_file) do |handle|
+          otu_names = handle.gets.strip.split(',')[1..-1]
+          all_otu_names += otu_names.to_set
+
+          handle.each do |line|
+            line = line.strip.split(',')
+            sample = File.basename(input_file)
+            all_samples << sample
+            read_counts = line[1..-1]
+            otu_names.zip(read_counts) do |name, count|
+              sample_name_count[sample][name] = count
+            end
+          end
+        end
+      end
+
+      # save to csv
+      File.open(output, 'w') do |handle|
+        header = all_otu_names.to_a.sort
+        handle.puts "-,#{header.join(',')}"
+
+        all_samples.to_a.sort.each do |sample|
+          handle.print "#{sample}"
+          header.each do |name|
+            handle.print ",#{sample_name_count[sample][name]}"
+          end
+          handle.print "\n"
+        end
+      end
+
+
+    end
+  end
+end

data/lib/lederhosen/tasks/otu_table.rb

@@ -33,13 +33,19 @@ module Lederhosen
       level_sample_cluster_count = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = Hash.new { |h, k| h[k] = 0 } } }
 
       all_names = Hash.new { |h, k| h[k] = Set.new }
-      pbar = ProgressBar.new "loading", input.size
+
+      # create a progress bar with the total number of bytes of
+      # the files we're slurping up
+      pbar = ProgressBar.new "loading", input.map{ |x| File.size(x) }.reduce(&:+)
 
       # Load cluster table
       input.each do |input_file|
-        pbar.inc
         File.open(input_file) do |handle|
           handle.each do |line|
+
+            # increase progressbar by the number of bytes in each line
+            pbar.inc line.unpack('*C').size
+
             dat = parse_usearch_line(line.strip)
             next if dat.nil?
 

data/lib/lederhosen/version.rb

@@ -3,7 +3,7 @@ module Lederhosen
     MAJOR = 1
     MINOR = 1
     CODENAME = 'Apfelstrudel' # changes for minor versions
-    PATCH = 0
+    PATCH = 1
 
     STRING = [MAJOR, MINOR, PATCH].join('.')
   end

data/readme.md

@@ -54,10 +54,12 @@ Cluster reads using USEARCH. Output is a uc file.
 
     lederhosen cluster --input=trimmed/*.fasta --identity=0.95 --output=clusters_95.uc --database=taxcollector.udb
 
-### Generate OTU tables
+### Generate OTU table(s)
 
 Create an OTU abundance table where rows are samples and columns are clusters. The entries are the number of reads for that cluster in a sample.
 
-    lederhosen otu_table --clusters=clusters_95.uc --output=genus.csv --level=genus
+    lederhosen otu_table --clusters=clusters_95.uc --prefix=otu_table --level=domain phylum class order family genus species
 
-Level can be Kingdom, Domain, Phylum, Class, Order, Family or Genus.
+This will create the files:
+
+    otu_table.domain.csv, ..., otu_table.species.csv

data/spec/cli_spec.rb

@@ -37,6 +37,11 @@ describe Lederhosen::CLI do
     $?.success?.should be_true
   end
 
+  it 'should combine OTU abundance matrices' do
+    `./bin/lederhosen join_otu_tables --input=#{$test_dir}/otu_table*.csv --output=#{$test_dir}/merged.csv`
+    $?.success?.should be_true
+  end
+
   it 'should split a fasta file into smaller fasta files (optionally gzipped)' do
     `./bin/lederhosen split_fasta --input=#{$test_dir}/trimmed/ILT_L_9_B_001.fasta --out-dir=#{$test_dir}/split/ --gzip true -n 100`
     $?.success?.should be_true

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lederhosen
 version: !ruby/object:Gem::Version 
-  hash: 19
+  hash: 17
   prerelease: 
   segments: 
   - 1
   - 1
-  - 0
-  version: 1.1.0
+  - 1
+  version: 1.1.1
 platform: ruby
 authors: 
 - Austin G. Davis-Richardson
@@ -123,6 +123,7 @@ files:
 - lib/lederhosen.rb
 - lib/lederhosen/cli.rb
 - lib/lederhosen/tasks/cluster.rb
+- lib/lederhosen/tasks/join_otu_tables.rb
 - lib/lederhosen/tasks/make_udb.rb
 - lib/lederhosen/tasks/otu_filter.rb
 - lib/lederhosen/tasks/otu_table.rb